Upload app.py

app.py

@@ -38,6 +38,7 @@ UI = {
     "fo": {"w":"Orð", "t":"Mark", "s":"Útgreining", "m":"Útgreinað marking"},
     "en": {"w":"Word","t":"Tag", "s":"Analysis", "m":"Expanded tags"},
 }
+
 MODEL_LINK = "https://huggingface.co/Setur/BRAGD"
 
 # Theme color: #89AFA9 (+ close shades) + system font
@@ -49,14 +50,11 @@ CSS = """
 body, .gradio-container, .prose, .markdown, textarea, input, select, button, table{
   font-family:-apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Arial, "Noto Sans", sans-serif !important;
 }
-
-/* Buttons */
 .gr-button-primary, button.primary, .primary{
   background:var(--primary-500)!important; border-color:var(--primary-600)!important; color:#0b1b19!important;
 }
 .gr-button-primary:hover, button.primary:hover, .primary:hover{ background:var(--primary-600)!important; }
 a{ color:var(--primary-700)!important; }
-.gr-button-primary{ padding: 0.32rem 0.75rem !important; font-size: 0.95rem !important; }
 
 /* Dataframe column wrapping: keep Orð + Mark on one line */
 .gr-dataframe table td:nth-child(1),
@@ -67,18 +65,68 @@ a{ color:var(--primary-700)!important; }
 .gr-dataframe table td:nth-child(2),
 .gr-dataframe table th:nth-child(2){
   white-space: nowrap !important;
-  width: 20% !important;
+  width: 18% !important;
   font-family: ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace !important;
 }
 .gr-dataframe table td:nth-child(3),
 .gr-dataframe table th:nth-child(3){
   white-space: normal !important;
-  width: 62% !important;
+  width: 64% !important;
+}
+
+/* Results header: make it a clean left-title / right-language bar (no grey blocks) */
+#results_hdr{
+  display:flex;
+  align-items:center;
+  justify-content:space-between;
+  gap: 12px;
+  padding: 0;
+  background: transparent !important;
+}
+#results_hdr > div{
+  background: transparent !important;
+  padding: 0 !important;
+  margin: 0 !important;
+  box-shadow: none !important;
+  border: 0 !important;
 }
 
-/* Compact dropdown on the right (avoid huge grey container) */
-#lang_dd { max-width: 150px; min-width: 150px; margin-left: auto; }
-#lang_dd > div { width: 150px !important; }
+/* Language toggle (radio styled as segmented buttons) */
+.lang_toggle{
+  display:flex;
+  gap: 8px;
+  justify-content:flex-end;
+  align-items:center;
+}
+.lang_toggle fieldset{
+  border: 0 !important;
+  padding: 0 !important;
+  margin: 0 !important;
+}
+.lang_toggle .wrap{
+  display:flex !important;
+  gap: 8px !important;
+}
+.lang_toggle input{
+  display:none !important; /* removes cursor + text field behavior entirely */
+}
+.lang_toggle label{
+  cursor:pointer;
+  padding: 8px 12px;
+  border-radius: 10px;
+  border: 1px solid rgba(0,0,0,.12);
+  background: white;
+  user-select:none;
+  font-size: 0.95rem;
+}
+.lang_toggle input:checked + span,
+.lang_toggle label.selected{
+  background: var(--primary-100) !important;
+  border-color: var(--primary-500) !important;
+}
+
+/* Slightly smaller primary button */
+.gr-button-primary{ padding: 0.35rem 0.85rem !important; font-size: 0.95rem !important; }
 """
 
 # ----------------------------
@@ -234,14 +282,6 @@ VOICE_ANALYSIS = {
 }
 
 def analysis_text(vec: torch.Tensor, lang: str) -> str:
-    """
-    Útgreining / Analysis:
-    - plain words (no letters/hyphens)
-    - pronouns: start at subcategory, not word class
-    - conjunctions: subcategory already includes 'sambindingarorð' in label
-    - DGd: show only fyriseting/preposition
-    - supine: show only supine + voice (drop verb/number/tense/person etc.)
-    """
     lang = "fo" if lang=="fo" else "en"
     tag = vector_to_tag(vec)
     wc = wc_code(vec)
@@ -259,7 +299,7 @@ def analysis_text(vec: torch.Tensor, lang: str) -> str:
 
     parts = []
 
-    # Pronouns + conjunctions: start at subcategory (the label already contains the head)
+    # Pronouns + conjunctions: subcategory already carries the head noun
     if wc in {"P","C"}:
         subc = group_code(vec, "subcategory")
         subl = clean_label(label_for(lang, "subcategory", wc, subc) or "")
@@ -275,7 +315,7 @@ def analysis_text(vec: torch.Tensor, lang: str) -> str:
         if not c:
             continue
         if wc in {"P","C"} and g == "subcategory":
-            continue  # already added
+            continue
         if (wc, g, c) in HIDE_IN_ANALYSIS:
             continue
 
@@ -290,7 +330,6 @@ def analysis_text(vec: torch.Tensor, lang: str) -> str:
     return ", ".join(parts)
 
 def expanded_text(vec: torch.Tensor, lang: str) -> str:
-    """Útgreinað marking / Expanded tags: codes + labels."""
     lang = "fo" if lang=="fo" else "en"
     wc = wc_code(vec)
     parts = []
@@ -308,7 +347,7 @@ def expanded_text(vec: torch.Tensor, lang: str) -> str:
     return "; ".join([p for p in parts if p])
 
 def compute_codes_by_wc():
-    codes = defaultdict(lambda: defaultdict(set))  # wc -> group -> set(code)
+    codes = defaultdict(lambda: defaultdict(set))
     for arr in tag_to_features.values():
         arr = np.array(arr)
 
@@ -333,7 +372,6 @@ def compute_codes_by_wc():
 CODES_BY_WC = compute_codes_by_wc()
 
 def build_overview(lang: str) -> str:
-    """Markayvirlit / Tag Overview under each word class (codes used in current CSV)."""
     lang = "fo" if lang=="fo" else "en"
     title = "### Markayvirlit" if lang=="fo" else "### Tag Overview"
     lines = [title, ""]
@@ -346,7 +384,6 @@ def build_overview(lang: str) -> str:
             cs = sorted(CODES_BY_WC[wc].get(g, set()))
             if not cs:
                 continue
-
             group_name = {
                 "fo": {
                     "subcategory":"Undirflokkur", "gender":"Kyn", "number":"Tal", "case":"Fall",
@@ -456,7 +493,7 @@ def render(rows_state, lang: str):
 theme = gr.themes.Soft()
 
 with gr.Blocks(theme=theme, css=CSS, title="Marka") as demo:
-    # New layout: textbox left, info right (button under info)
+    # Layout: textbox left, info right, button under info
     with gr.Row(equal_height=True):
         with gr.Column(scale=2):
             inp = gr.Textbox(
@@ -464,7 +501,7 @@ with gr.Blocks(theme=theme, css=CSS, title="Marka") as demo:
                 placeholder="Skriva her ... / Type here ...",
                 show_label=False,
             )
-        with gr.Column(scale=1, min_width=280):
+        with gr.Column(scale=1, min_width=320):
             gr.Markdown(
                 "### Marka\n"
                 "Skriv setningin í kassan vinstrumegin og fá hann markaðan.\n\n"
@@ -474,19 +511,16 @@ with gr.Blocks(theme=theme, css=CSS, title="Marka") as demo:
 
     state = gr.State([])
 
-    # Results header row (components hide until first run)
-    with gr.Row():
-        with gr.Column(scale=5):
-            results_title = gr.Markdown("### Úrslit / Results", visible=False)
-        with gr.Column(scale=1, min_width=170):
-            lang = gr.Dropdown(
-                choices=[("Føroyskt","fo"), ("English","en")],
-                value="fo",
-                show_label=False,
-                filterable=False,
-                elem_id="lang_dd",
-                visible=False,
-            )
+    # Results header row (hidden until first run)
+    with gr.Row(elem_id="results_hdr"):
+        results_title = gr.Markdown("### Úrslit / Results", visible=False)
+        lang = gr.Radio(
+            choices=[("Føroyskt","fo"), ("English","en")],
+            value="fo",
+            show_label=False,
+            visible=False,
+            elem_classes=["lang_toggle"],
+        )
 
     out_df = gr.Dataframe(
         value=pd.DataFrame(columns=[UI["fo"]["w"], UI["fo"]["t"], UI["fo"]["s"]]),
@@ -498,8 +532,8 @@ with gr.Blocks(theme=theme, css=CSS, title="Marka") as demo:
         visible=False,
     )
 
-    # Hide Expanded tags accordion until tagged
-    with gr.Accordion("Útgreinað marking / Expanded tags", open=False, visible=False) as expanded_acc:
+    expanded_acc = gr.Accordion("Útgreinað marking / Expanded tags", open=False, visible=False)
+    with expanded_acc:
         out_mean_df = gr.Dataframe(
             value=pd.DataFrame(columns=[UI["fo"]["w"], UI["fo"]["t"], UI["fo"]["m"]]),
             wrap=True,
@@ -507,11 +541,11 @@ with gr.Blocks(theme=theme, css=CSS, title="Marka") as demo:
             show_label=False,
             row_count=(0, "fixed"),
             col_count=(3, "fixed"),
-            visible=True,
         )
 
-    with gr.Accordion("Markayvirlit / Tag Overview", open=False):
-        overview_md = gr.Markdown("", visible=False)
+    overview_acc = gr.Accordion("Markayvirlit / Tag Overview", open=False, visible=False)
+    with overview_acc:
+        overview_md = gr.Markdown("")
 
     def on_tag(sentence, lang_choice):
         rows = run_model(sentence)
@@ -519,11 +553,12 @@ with gr.Blocks(theme=theme, css=CSS, title="Marka") as demo:
         return (
             rows,
             gr.update(value=df_main, visible=True),
-            gr.update(value=df_mean, visible=True),
-            gr.update(value=overview, visible=True),
+            gr.update(value=df_mean),
+            gr.update(value=overview),
             gr.update(visible=True),   # results_title
             gr.update(visible=True),   # lang
             gr.update(visible=True),   # expanded_acc
+            gr.update(visible=True),   # overview_acc
         )
 
     def on_lang(rows, lang_choice):
@@ -537,7 +572,7 @@ with gr.Blocks(theme=theme, css=CSS, title="Marka") as demo:
     btn.click(
         on_tag,
         inputs=[inp, lang],
-        outputs=[state, out_df, out_mean_df, overview_md, results_title, lang, expanded_acc],
+        outputs=[state, out_df, out_mean_df, overview_md, results_title, lang, expanded_acc, overview_acc],
         queue=False,
     )